Epileptic seizure detection in EEGs signals using a fast weighted horizontal visibility algorithm

• Published in: Computer methods and programs in biomedicine Vol. 115; no. 2; pp. 64 - 75
• Main Authors: Zhu, Guohun, Li, Yan, Wen, Peng (Paul)
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ireland Ltd 01.07.2014; Elsevier
• Subjects: Algorithmics. Computability. Computer arithmetics; Algorithms; Applied sciences; Biological and medical sciences; Computational complexity; Computer science; control theory; systems; Computer Simulation; Databases, Factual - statistics & numerical data; Diagnosis, Computer-Assisted - methods; Diagnosis, Computer-Assisted - statistics & numerical data; Electrodiagnosis. Electric activity recording; Electroencephalography - statistics & numerical data; Epilepsy; Epilepsy - diagnosis; Exact sciences and technology; Fourier Analysis; Headache. Facial pains. Syncopes. Epilepsia. Intracranial hypertension. Brain oedema. Cerebral palsy; Humans; Information retrieval. Graph; Internal Medicine; Investigative techniques, diagnostic techniques (general aspects); Mean degree; Mean strength; Medical sciences; Nervous system; Nervous system (semeiology, syndromes); Neurology; Nonlinear Dynamics; Other; Theoretical computing; Weighted horizontal visibility graph; Mean degree; Mean strength; Computational complexity; Weighted horizontal visibility graph; Epilepsy; Chaos; Fast Fourier transformation; Time series; Electroencephalography; Entropy; Graph theory; Pattern recognition; Weighted graph; Experimental result; Classification; Mental disorder; Selection criterion; Noise immunity; Feature extraction; Visibility; Fast algorithm; Pattern extraction; Strength
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2014.04.001

•Developing a fast algorithm for constructing a network from a time series in linear time.•Discriminating between healthy and seizure EEG signals with 100% accuracy with only two features.•Extracted features from a time series is faster and more robust to against noise than those based on FFT. This paper proposes a fast weighted horizontal visibility graph constructing algorithm (FWHVA) to identify seizure from EEG signals. The performance of the FWHVA is evaluated by comparing with Fast Fourier Transform (FFT) and sample entropy (SampEn) method. Two noise-robustness graph features based on the FWHVA, mean degree and mean strength, are investigated using two chaos signals and five groups of EEG signals. Experimental results show that feature extraction using the FWHVA is faster than that of SampEn and FFT. And mean strength feature associated with ictal EEG is significant higher than that of healthy and inter-ictal EEGs. In addition, an 100% classification accuracy for identifying seizure from healthy shows that the features based on the FWHVA are more promising than the frequency features based on FFT and entropy indices based on SampEn for time series classification.